Counter-Interference Adapter for Multilingual Machine Translation
Yaoming Zhu, Jiangtao Feng, Chengqi Zhao, Mingxuan Wang, Lei Li
Abstract
Developing a unified multilingual model has been a long pursuing goal for machine translation. However, existing approaches suffer from performance degradation - a single multilingual model is inferior to separately trained bilingual ones on rich-resource languages. We conjecture that such a phenomenon is due to interference brought by joint training with multiple languages. To accommodate the issue, we propose CIAT, an adapted Transformer model with a small parameter overhead for multilingual machine translation. We evaluate CIAT on multiple benchmark datasets, including IWSLT, OPUS-100, and WMT. Experiments show that the CIAT consistently outperforms strong multilingual baselines on 64 of total 66 language directions, 42 of which have above 0.5 BLEU improvement.
BibTeX
@inproceedings{zhu-etal-2021-counter-interference,
title = "Counter-Interference Adapter for Multilingual Machine Translation",
author = "Zhu, Yaoming and
Feng, Jiangtao and
Zhao, Chengqi and
Wang, Mingxuan and
Li, Lei",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.240/",
doi = "10.18653/v1/2021.findings-emnlp.240",
pages = "2812--2823"
}